Abstract
The development of mobile networks and implementation of new standards, such as 5G and 6G, in the future, will lead to increased traffic volume in the network and new types of traffic creation. Also, new traffic types demand specific service requirements. Currently, existing traffic processing methods are not adapted to such changes, which can impair the Quality of Service. A possible solution for improving the efficiency of information processing is introducing new algorithms for classifying and prioritizing traffic. That is why in this work, the main focus is on analyzing the effectiveness of machine learning algorithms to solve the problem of traffic classification in mobile networks in real-time. The accuracy of classification and performance for the most common machine learning algorithms is analyzed, and the criterion of classification accuracy determines the optimal algorithm to achieve the goal. The results of the comparative analysis showed that the best accuracy could be achieved when using ANN algorithms (the number of latent network layers is 200) and RF. At the same time, the advantages of ANN include high efficiency and reliability of information processing and simple algorithm learning. Also, the RF algorithm is a quick and powerful classification algorithm, but it has shortcomings during the interpretation of the solution and works poorly for small data. In addition, the work assessment of the importance of the dataset fields for classification was evaluated. These improvements can be implemented both on final devices and base stations. They will improve the quality of classification, clustering, and processing of packets, which will generally increase the efficiency of the intellectual mobile network management system. Further development of the topic may be using the studied algorithms to solve the problems of detecting anomalies in traffic to increase the network’s security.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.